Weakly-Supervised Reinforcement Learning for Controllable Behavior
This addresses the challenge of task selection in RL for agents in complex environments, though it appears incremental as it builds on existing weak supervision and disentanglement ideas.
The paper tackles the problem of constraining the vast space of possible tasks in reinforcement learning to semantically meaningful ones using weak supervision, resulting in substantial performance gains on challenging vision-based continuous control problems.
Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient exploration and provides a representation that captures distance between states. On a variety of challenging, vision-based continuous control problems, our approach leads to substantial performance gains, particularly as the complexity of the environment grows.